Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 220
    Prev
    Next
    INDEX
    Explanations

    terms related to compression and tightness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases related to compression or squeezing.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderSide
    -0.51
    contentLoaded
    -0.49
    LookAnd
    -0.48
    قایناق‌لار
    -0.47
    Aiheesta
    -0.47
     NavController
    -0.47
    tableFuture
    -0.47
    demort
    -0.46
    Cyfarwyddwr
    -0.43
    Slf
    -0.42
    POSITIVE LOGITS
     tight
    1.02
    tight
    0.99
     squeeze
    0.98
    Tight
    0.98
     Tight
    0.94
     squeezing
    0.88
     tightening
    0.86
     compress
    0.85
     tighter
    0.85
     tightened
    0.85
    Activations Density 0.264%

    No Known Activations